Class8_20230330_DataVisualization_Apichat
Apichat Photi-A
2023-03-30
#load package
library(ggplot2)
library(ggthemes)
library(ggrepel)
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.0 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ lubridate 1.9.2 ✔ tibble 3.1.8
## ✔ purrr 1.0.1 ✔ tidyr 1.3.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the ]8;;http://conflicted.r-lib.org/conflicted package]8;; to force all conflicts to become errorslibrary(socviz)##review data
election |>
select(state, total_vote, r_points, pct_trump, party, census) |>
sample_n(5)## # A tibble: 5 × 6
## state total_vote r_points pct_trump party census
## <chr> <dbl> <dbl> <dbl> <chr> <chr>
## 1 Michigan 4824542 0.220 47.2 Republican Midwest
## 2 Oregon 2001336 -11.0 39.1 Democratic West
## 3 Alaska 318608 14.7 51.3 Republican West
## 4 New York 7721795 -22.5 36.5 Democratic Northeast
## 5 Oklahoma 1452992 36.4 65.3 Republican Southparty_colors <- c("#2E74C0", "#CB454A")
p0 <- ggplot(data = subset(election, st %nin% "DC"),
mapping = aes(x = r_points,
y = reorder(state, r_points), color = party))
p1 <- p0 + geom_vline(xintercept = 0, color = "gray30") + geom_point(size = 2)
p2 <- p1 + scale_color_manual(values = party_colors)
p3 <- p2 + scale_x_continuous(breaks = c( -30, -20, -10, 0, 10, 20, 30, 40),
labels = c("30\n (Clinton)", "20", "10", "0", "10", "20", "30", "40\n(Trump)"))
p3 + facet_wrap(~ census,
ncol=1, scales="free_y") +
guides(color=FALSE) + labs(x = "Point Margin", y = "") +
theme(axis.text=element_text(size=8))## Warning: The `<scale>` argument of `guides()` cannot be `FALSE`. Use "none" instead as
## of ggplot2 3.3.4.
install and preview maps
#install.packages("maps")
library(maps)##
## Attaching package: 'maps'## The following object is masked from 'package:purrr':
##
## mapus_states <- map_data("state")
head(us_states)## long lat group order region subregion
## 1 -87.46201 30.38968 1 1 alabama <NA>
## 2 -87.48493 30.37249 1 2 alabama <NA>
## 3 -87.52503 30.37249 1 3 alabama <NA>
## 4 -87.53076 30.33239 1 4 alabama <NA>
## 5 -87.57087 30.32665 1 5 alabama <NA>
## 6 -87.58806 30.32665 1 6 alabama <NA>#Create a black and white map
p <- ggplot(data = us_states, mapping = aes(x = long,
y = lat,
group = group))
p + geom_polygon(fill = "white", color = "black")
#Add the colour
p <- ggplot(data = us_states, aes(x = long,
y = lat,
group = group,
fill = region))
p + geom_polygon(color = "gray90", linewidth = 0.1) + guides(fill = FALSE)
library(mapproj) #require for coord_map
#Add the colour
p <- ggplot(data = us_states, aes(x = long,
y = lat,
group = group,
fill = region))
p + geom_polygon(color = "gray90", size = 0.1) + coord_map(projection = "albers", lat0 = 39, lat1 = 45) +
guides(fill = FALSE)## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
Merge election and map datasets
election$region <- tolower(election$state)
us_states_elec <- left_join(us_states, election, by='region')
head(us_states_elec)## long lat group order region subregion state st fips total_vote
## 1 -87.46201 30.38968 1 1 alabama <NA> Alabama AL 1 2123372
## 2 -87.48493 30.37249 1 2 alabama <NA> Alabama AL 1 2123372
## 3 -87.52503 30.37249 1 3 alabama <NA> Alabama AL 1 2123372
## 4 -87.53076 30.33239 1 4 alabama <NA> Alabama AL 1 2123372
## 5 -87.57087 30.32665 1 5 alabama <NA> Alabama AL 1 2123372
## 6 -87.58806 30.32665 1 6 alabama <NA> Alabama AL 1 2123372
## vote_margin winner party pct_margin r_points d_points pct_clinton
## 1 588708 Trump Republican 0.2773 27.72 -27.72 34.36
## 2 588708 Trump Republican 0.2773 27.72 -27.72 34.36
## 3 588708 Trump Republican 0.2773 27.72 -27.72 34.36
## 4 588708 Trump Republican 0.2773 27.72 -27.72 34.36
## 5 588708 Trump Republican 0.2773 27.72 -27.72 34.36
## 6 588708 Trump Republican 0.2773 27.72 -27.72 34.36
## pct_trump pct_johnson pct_other clinton_vote trump_vote johnson_vote
## 1 62.08 2.09 1.46 729547 1318255 44467
## 2 62.08 2.09 1.46 729547 1318255 44467
## 3 62.08 2.09 1.46 729547 1318255 44467
## 4 62.08 2.09 1.46 729547 1318255 44467
## 5 62.08 2.09 1.46 729547 1318255 44467
## 6 62.08 2.09 1.46 729547 1318255 44467
## other_vote ev_dem ev_rep ev_oth census
## 1 31103 0 9 0 South
## 2 31103 0 9 0 South
## 3 31103 0 9 0 South
## 4 31103 0 9 0 South
## 5 31103 0 9 0 South
## 6 31103 0 9 0 Southplot election data on a map
party_colors <- c("#2E74C0", "#CB454A")
p0 <- ggplot(data = us_states_elec,
mapping = aes(x = long,
y = lat,
group = group,
fill = party))
p1 <- p0 + geom_polygon(color = "gray90", size = 0.1) +
coord_map(projection = "albers", lat0 = 39, lat1 = 45)
p2 <- p1 + scale_fill_manual(values = party_colors) +
labs(title = "Election Results 2016", fill = NULL)
p2 + theme_map()
#review country datasets
county_map |>
sample_n(5)## long lat order hole piece group id
## 1 150909.0 299017.78 129260 FALSE 1 0500000US38091.1 38091
## 2 937623.0 -910823.99 103256 FALSE 1 0500000US29155.1 29155
## 3 322397.9 -362124.42 111994 FALSE 1 0500000US31177.1 31177
## 4 2199227.9 40672.03 33431 FALSE 1 0500000US09003.1 09003
## 5 551637.4 -943608.59 19423 FALSE 1 0500000US05015.1 05015county_data |>
select(id, name, state, pop_dens) |>
sample_n(5)## id name state pop_dens
## 1 27095 Mille Lacs County MN [ 10, 50)
## 2 40131 Rogers County OK [ 100, 500)
## 3 21017 Bourbon County KY [ 50, 100)
## 4 22065 Madison Parish LA [ 10, 50)
## 5 31051 Dixon County NE [ 10, 50)#merge datasets
county_full <- left_join(county_map, county_data, by = "id")
head(county_full)## long lat order hole piece group id name
## 1 1225889 -1275020 1 FALSE 1 0500000US01001.1 01001 Autauga County
## 2 1235324 -1274008 2 FALSE 1 0500000US01001.1 01001 Autauga County
## 3 1244873 -1272331 3 FALSE 1 0500000US01001.1 01001 Autauga County
## 4 1244129 -1267515 4 FALSE 1 0500000US01001.1 01001 Autauga County
## 5 1272010 -1262889 5 FALSE 1 0500000US01001.1 01001 Autauga County
## 6 1276797 -1295514 6 FALSE 1 0500000US01001.1 01001 Autauga County
## state census_region pop_dens pop_dens4 pop_dens6 pct_black pop
## 1 AL South [ 50, 100) [ 45, 118) [ 82, 215) [15.0,25.0) 55395
## 2 AL South [ 50, 100) [ 45, 118) [ 82, 215) [15.0,25.0) 55395
## 3 AL South [ 50, 100) [ 45, 118) [ 82, 215) [15.0,25.0) 55395
## 4 AL South [ 50, 100) [ 45, 118) [ 82, 215) [15.0,25.0) 55395
## 5 AL South [ 50, 100) [ 45, 118) [ 82, 215) [15.0,25.0) 55395
## 6 AL South [ 50, 100) [ 45, 118) [ 82, 215) [15.0,25.0) 55395
## female white black travel_time land_area hh_income su_gun4 su_gun6 fips
## 1 51.5 78.1 18.4 26.2 594.44 53682 [11,54] [10,12) 1001
## 2 51.5 78.1 18.4 26.2 594.44 53682 [11,54] [10,12) 1001
## 3 51.5 78.1 18.4 26.2 594.44 53682 [11,54] [10,12) 1001
## 4 51.5 78.1 18.4 26.2 594.44 53682 [11,54] [10,12) 1001
## 5 51.5 78.1 18.4 26.2 594.44 53682 [11,54] [10,12) 1001
## 6 51.5 78.1 18.4 26.2 594.44 53682 [11,54] [10,12) 1001
## votes_dem_2016 votes_gop_2016 total_votes_2016 per_dem_2016 per_gop_2016
## 1 5908 18110 24661 0.2395685 0.7343579
## 2 5908 18110 24661 0.2395685 0.7343579
## 3 5908 18110 24661 0.2395685 0.7343579
## 4 5908 18110 24661 0.2395685 0.7343579
## 5 5908 18110 24661 0.2395685 0.7343579
## 6 5908 18110 24661 0.2395685 0.7343579
## diff_2016 per_dem_2012 per_gop_2012 diff_2012 winner partywinner16 winner12
## 1 12202 0.2657577 0.7263374 11012 Trump Republican Romney
## 2 12202 0.2657577 0.7263374 11012 Trump Republican Romney
## 3 12202 0.2657577 0.7263374 11012 Trump Republican Romney
## 4 12202 0.2657577 0.7263374 11012 Trump Republican Romney
## 5 12202 0.2657577 0.7263374 11012 Trump Republican Romney
## 6 12202 0.2657577 0.7263374 11012 Trump Republican Romney
## partywinner12 flipped
## 1 Republican No
## 2 Republican No
## 3 Republican No
## 4 Republican No
## 5 Republican No
## 6 Republican No#plotting population density
p <- ggplot(data = county_full,
mapping = aes(x = long,
y = lat,
fill = pop_dens,
group = group))
p1 <- p + geom_polygon(color = "gray90", size = 0.05) +
coord_equal()
p2 <- p1 + scale_fill_brewer(palette="Blues",
labels = c("0-10", "10-50", "50-100", "100-500", "500-1,000", "1,000-5,000", ">5,000"))
p2 + labs(fill = "Population per nsquare mile") +
theme_map() +
guides(fill = guide_legend(nrow = 1)) +
theme(legend.position = "bottom")
#the range of pop per sq mile depends on the “pop_den” range #if we need
to change these ranges, me must reclassify before plotting the
graph.
#Reference: [https://app.diagrams.net/]
##install
#install.packages("DiagrammeR")
library(DiagrammeR)
#making basic flowchart
grViz(diagram = "digraph flowchart {
tab1 [label = '@@1', fontname = arial, shape = plaintext, fontcolor = blue]
tab2 [label = '@@2', fontname = arial, shape = plaintext, fontcolor = blue]
tab3 [label = '@@3', fontname = arial, shape = plaintext, fontcolor = blue]
tab4 [label = '@@4', fontname = arial, shape = plaintext]
tab1 -> tab2 -> tab3 [color = red, arrowhead = vee, arrowsize = 1, penwidth = 5];
tab2 -> tab4
}
[1]: 'Artefact collection in field'
[2]: 'Preliminary dating of artefacts (visual)'
[3]: 'Artefacts sent to lab for dating'
[4]: 'Artefacts put in storage'
")